Automatic Segmentation of the Prostate on 3D Trans-rectal Ultrasound Images using Statistical Shape Models and Convolutional Neural Networks
This work addresses the need for fast and accurate prostate segmentation in TRUS images for medical interventions, though it is incremental as it builds on existing methods like CNNs and shape models.
The authors tackled the problem of segmenting the prostate in 3D trans-rectal ultrasound (TRUS) images, which is challenging due to low contrast and noise, by combining statistical shape models from MRI with convolutional neural networks, achieving improved accuracy in defining gland boundaries at the base and apex.
In this work we propose to segment the prostate on a challenging dataset of trans-rectal ultrasound (TRUS) images using convolutional neural networks (CNNs) and statistical shape models (SSMs). TRUS is commonly used for a number of image-guided interventions on the prostate. Fast and accurate segmentation on the organ in these images is crucial to planning and fusion with other modalities such as magnetic resonance images (MRIs) . However, TRUS has limited soft tissue contrast and signal to noise ratio which makes the task of segmenting the prostate challenging and subject to inter-observer and intra-observer variability. This is especially problematic at the base and apex where the gland boundary is hard to define. In this paper, we aim to tackle this problem by taking advantage of shape priors learnt on an MR dataset which has higher soft tissue contrast allowing the prostate to be contoured more accurately. We use this shape prior in combination with a prostate tissue probability map computed by a CNN for segmentation.